Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
dball
/
zephyr-7b-dpo-qlora
like
0
PEFT
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
mistral
alignment-handbook
Generated from Trainer
trl
dpo
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
2
Train
Use this model
refs/pr/2
zephyr-7b-dpo-qlora
/
train_results.json
dball
Model save
84f5259
verified
7 months ago
raw
Copy download link
history
blame
No virus
199 Bytes
{
"epoch"
:
1.0
,
"train_loss"
:
0.0026284047499827543
,
"train_runtime"
:
361.3652
,
"train_samples"
:
61135
,
"train_samples_per_second"
:
169.178
,
"train_steps_per_second"
:
21.145
}